← all datasets

OCR-VQA

Emerging

3papers using it

2,179HF downloads

60HF likes

2021first seen

Dataset Card for "OCR-VQA" More Information needed

🤗 Hugging Face

Papers using OCR-VQA (3)

Vision Verification Enhanced Fusion of VLMs for Efficient Visual Reasoning2026

BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions2023 · 12 cites

LaTr: Layout-Aware Transformer for Scene-Text VQA2021 · 2 cites

OCR-VQA — datasets — multimodal